{"id":"https://openalex.org/W4404310331","doi":"https://doi.org/10.1587/transinf.2024edl8061","title":"APW: Asymmetric Padded Winograd to Reduce Thread Divergence for Computational Efficiency on SIMT Architecture","display_name":"APW: Asymmetric Padded Winograd to Reduce Thread Divergence for Computational Efficiency on SIMT Architecture","publication_year":2024,"publication_date":"2024-11-13","ids":{"openalex":"https://openalex.org/W4404310331","doi":"https://doi.org/10.1587/transinf.2024edl8061"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edl8061","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8061","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/5/E108.D_2024EDL8061/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/5/E108.D_2024EDL8061/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087071976","display_name":"Won\u2010Ho Lee","orcid":"https://orcid.org/0009-0000-5158-1202"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonho LEE","raw_affiliation_strings":["Yeungnam University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yeungnam University","institution_ids":["https://openalex.org/I55240360"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063534646","display_name":"Jong Wook Kwak","orcid":"https://orcid.org/0000-0002-6639-3738"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Wook KWAK","raw_affiliation_strings":["Yeungnam University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yeungnam University","institution_ids":["https://openalex.org/I55240360"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55240360"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16697736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E108.D","issue":"5","first_page":"436","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9575999975204468,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9575999975204468,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12222","display_name":"IoT-based Smart Home Systems","score":0.9435999989509583,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7893878221511841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7725679874420166},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5320084691047668},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5257607102394104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35912641882896423},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33429181575775146},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07516497373580933},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07505065202713013}],"concepts":[{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7893878221511841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725679874420166},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5320084691047668},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5257607102394104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35912641882896423},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33429181575775146},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07516497373580933},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07505065202713013},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024edl8061","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8061","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/5/E108.D_2024EDL8061/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edl8061","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8061","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/5/E108.D_2024EDL8061/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.75,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404310331.pdf","grobid_xml":"https://content.openalex.org/works/W4404310331.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3098382995","https://openalex.org/W3192697904","https://openalex.org/W4220858218","https://openalex.org/W4323313312","https://openalex.org/W4327808157","https://openalex.org/W4394593142"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2033778626","https://openalex.org/W2187110187","https://openalex.org/W2026780467","https://openalex.org/W2002371119","https://openalex.org/W2018697868","https://openalex.org/W4390492895","https://openalex.org/W2023832055","https://openalex.org/W2082485924"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3],"propose":[4],"Asymmetric":[5],"Padded":[6],"Winograd":[7],"called":[8],"APW,":[9],"designed":[10],"to":[11,35,89,101],"enhance":[12],"the":[13,52,95],"computational":[14,37],"efficiency":[15],"of":[16,54],"Winograd-based":[17,68],"convolution":[18,69],"algorithms":[19],"on":[20],"SIMT":[21],"architectures.":[22],"This":[23,58],"approach":[24],"resolves":[25],"thread":[26,73,83],"divergence,":[27],"which":[28],"typically":[29],"causes":[30],"delays":[31],"in":[32,86],"execution":[33,63,97],"due":[34],"uneven":[36],"distribution":[38],"across":[39],"threads.":[40],"By":[41],"integrating":[42],"asymmetric":[43],"padding":[44],"into":[45],"both":[46],"filters":[47],"and":[48,56,92],"inputs,":[49],"APW":[50,80],"unifies":[51],"size":[53],"sub-filters":[55],"sub-inputs.":[57],"uniformity":[59],"maintains":[60],"a":[61],"consistent":[62],"path":[64],"for":[65],"threads":[66],"throughout":[67],"process,":[70],"effectively":[71],"minimizing":[72],"divergence.":[74],"Our":[75],"experimental":[76],"results":[77],"demonstrate":[78],"that":[79],"substantially":[81],"reduces":[82],"divergence":[84],"observed":[85],"previous":[87],"work":[88],"nearly":[90],"zero":[91],"cuts":[93],"down":[94],"total":[96],"time":[98],"by":[99],"up":[100],"17.78%.":[102]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
